Scientific Lead, Applied Intelligence for Discovery

Lilly • San Francisco, CA

1d

About The Position

At Lilly, we unite caring with discovery to make life better for people around the world. We are a global healthcare leader headquartered in Indianapolis, Indiana. Our employees around the world work to discover and bring life-changing medicines to those who need them, improve the understanding and management of disease, and give back to our communities through philanthropy and volunteerism. We give our best effort to our work, and we put people first. We’re looking for people who are determined to make life better for people around the world.
The Opportunity
We are building something unprecedented, an AI foundation that will fundamentally change how drug discovery research is conducted.
The Applied Intelligence for Discovery (AI4D) team is a newly formed group within Lilly Research Laboratories that operates at the intersection of scientific delivery and core platform development. AI4D’s mission is to connecting scientists to petabyte-scale data through natural language interfaces, automated analysis workflows, and intelligent search — and to convert early deployments into repeatable system standards and evaluation practices that scale across therapeutic areas.
As a Generative AI Engineer, you will design, build, and operate the core AI systems that power this transformation: retrieval-augmented generation over internal scientific documents, text-to-SQL over complex omics databases, agentic workflows that automate multi-step analyses, and the evaluation infrastructure that able the next-generation of medicines for patients.

Requirements

• PhD in Computer Science, Data Science, or a related technical field with 0-3+ years of experience; or equivalent experience building production LLM systems; MS in Computer Science, Data Science, or a related technical field with 5+ years of experience; or equivalent experience building production LLM systems

Nice To Haves

• Experience building LLM-powered applications, including at least two of: RAG systems, text-to-SQL, agentic workflows, or fine-tuning pipelines
• Strong software engineering skills in Python with experience building production-grade systems
• Deep familiarity with the modern LLM ecosystem: embedding models, vector databases, and orchestration frameworks
• Experience designing evaluation frameworks for LLM systems — systematic approaches to measuring accuracy, detecting hallucinations, and tracking regressions
• Comfort working with complex, heterogeneous data — databases with hundreds of tables, specialized schemas, or domain-specific vocabularies
• Familiarity with cloud computing environments (AWS preferred), containerization (Docker), and CI/CD practices
• Experience in pharmaceutical, biotech, or life sciences environments
• Familiarity with biomedical data types (omics, clinical, molecular) or scientific databases
• Experience with MLOps/LLMOps tooling: experiment tracking, model registries, prompt versioning, A/B testing for AI systems
• Knowledge of biomedical ontologies (Gene Ontology, MeSH, ChEBI) or experience integrating domain-specific knowledge into LLM systems
• Experience building for regulated environments where auditability, reproducibility, and explainability are requirements

Responsibilities

• Design, build, and optimize RAG pipelines over internal publications, study reports, electronic lab notebooks, and other scientific documents
• Build hybrid retrieval systems combining vector search with structured metadata, knowledge graphs, and ontology-aware filtering
• Build and optimize text-to-SQL systems over Lilly’s databases, enabling scientists to query gene expression, proteomics, pathway, and variant data through natural language
• Develop schema documentation, semantic annotations, and gold-standard question/SQL pairs that bridge how scientists think about data and how it is stored
• Implement multi-step reasoning approaches (chain-of-thought, self-correction, Reflexion loops) to improve accuracy on complex scientific queries
• Design agentic AI workflows that chain database queries, bioinformatics tools, literature search, and visualization into automated multi-step scientific analyses
• Evaluate and integrate emerging orchestration frameworks (LangGraph, CrewAI, custom architectures) for scientific use cases
• Build evaluation frameworks measuring accuracy, reliability, and scientific validity of AI outputs

Benefits

• Full-time equivalent employees also will be eligible for a company bonus (depending, in part, on company and individual performance). In addition, Lilly offers a comprehensive benefit program to eligible employees, including eligibility to participate in a company-sponsored 401(k); pension; vacation benefits; eligibility for medical, dental, vision and prescription drug benefits; flexible benefits (e.g., healthcare and/or dependent day care flexible spending accounts); life insurance and death benefits; certain time off and leave of absence benefits; and well-being benefits (e.g., employee assistance program, fitness benefits, and employee clubs and activities).

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Ph.D. or professional degree